According to Bering's WeChat account, on October 15, Ant Bailing officially opened the open source of Ling-3.1-Flash, allowing the team to test the model's ability and reasoning efficiency in their own tasks and computing power environments. According to reports, the total parameters of LING-3.1-flash are about 560B, each token is activated about 25B, and supports up to 1M contexts.

Disclaimer:Webull uses external vendor Google Translation Service for news translations where we endeavour to ensure these are correct, however, we recommend that you please double-check this information accordingly. Webull is not responsible for translation errors or issues.